Daredevil-8B-abliterated

👁 image/jpeg

Abliterated version of mlabonne/Daredevil-8B using failspy's notebook.

It based on the technique described in the blog post "Refusal in LLMs is mediated by a single direction".

Thanks to Andy Arditi, Oscar Balcells Obeso, Aaquib111, Wes Gurnee, Neel Nanda, and failspy.

🔎 Applications

This is an uncensored model. You can use it for any application that doesn't require alignment, like role-playing.

Tested on LM Studio using the "Llama 3" preset.

⚡ Quantization

• GGUF: https://huggingface.co/mlabonne/Daredevil-8B-abliterated-GGUF

🏆 Evaluation

Open LLM Leaderboard

Daredevil-8B-abliterated is the second best-performing 8B model on the Open LLM Leaderboard in terms of MMLU score (27 May 24).

👁 image/png

Nous

Evaluation performed using LLM AutoEval. See the entire leaderboard here.

🌳 Model family tree

👁 image/png

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "mlabonne/Daredevil-8B-abliterated"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
 "text-generation",
 model=model,
 torch_dtype=torch.float16,
 device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

Base model

mlabonne/Daredevil-8B

(2)

Fine-tuned abliterated merge of the best Llama 3 8B model. Highest MMLU score in its category. • 5 items • Updated Aug 16, 2024 • 19